
Azure Ai
- 482k installs
- 1.3k repo stars
- Updated July 26, 2026
- microsoft/azure-skills
azure-ai is an agent skill that maps Azure AI Search, Speech, OpenAI, and Document Intelligence tasks to MCP tools, CLI commands, and SDK references.
About
The azure-ai skill is a Microsoft agent skill for Azure AI services spanning AI Search, Speech, Azure OpenAI, and Document Intelligence. It routes developers to the right service for full-text, vector, hybrid, and semantic search, plus speech-to-text, text-to-speech, transcription, and OCR form extraction. When Azure MCP is enabled, preferred commands include azure__search for index list, get, and query, and azure__speech for transcribe and synthesize. If MCP is unavailable, the skill points to /azure:setup or /mcp enablement and documents az search and az cognitiveservices CLI paths. Capability tables cover AI enrichment, speaker diarization, neural voices with SSML, and custom speech models. Condensed SDK guides link Python, TypeScript, .NET, and Java references for search documents, vision, transcription, translation, document intelligence, and content safety. Version 1.1.1 MIT-licensed metadata anchors the skill to official Microsoft Azure AI documentation patterns.
- Routes AI Search, Speech, OpenAI, and Document Intelligence tasks with service-specific use-when guidance.
- Prefers Azure MCP commands azure__search and azure__speech for index ops and transcription or synthesis.
- Documents full-text, vector, hybrid search plus AI enrichment for entities, OCR, and sentiment.
- Covers speech-to-text, text-to-speech, speaker diarization, and custom vocabulary models.
- Links condensed SDK quick references across Python, TypeScript, .NET, and Java client libraries.
Azure Ai by the numbers
- 482,491 all-time installs (skills.sh)
- Security screen: LOW risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
azure-ai capabilities & compatibility
Free skill; requires a paid Azure AI Services subscription and endpoint credentials.
- Capabilities
- azure ai service routing by task · mcp search index list, get, and query · mcp speech transcribe and synthesize · hybrid and vector search guidance · sdk quick reference linking · cli fallback via az search and az cognitiveservi
- Works with
- azure · openai
- Use cases
- api development · data analysis · orchestration
- Runs
- Local or remote
- Pricing
- Bring your own API key
What azure-ai says it does
When Azure MCP is enabled:
Hybrid search | Combined keyword + vector
Speaker diarization | Identify who spoke when
npx skills add https://github.com/microsoft/azure-skills --skill azure-aiAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 482k |
|---|---|
| repo stars | ★ 1.3k |
| Security audit | 3 / 3 scanners passed |
| Last updated | July 26, 2026 |
| Repository | microsoft/azure-skills ↗ |
Which Azure AI service and API should I use for vector search, speech transcription, GPT calls, or document OCR in my app?
Wire Azure AI Search, Speech, OpenAI, and Document Intelligence into apps via MCP tools or SDK quick references.
Who is it for?
Developers building on Azure who need guided routing across AI Search, Speech, OpenAI, and Document Intelligence.
Skip if: Skip for non-Azure clouds or Azure workloads unrelated to cognitive AI services.
When should I use this skill?
AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, or convert text to speech.
What you get
Correct Azure AI service selection with MCP command patterns or SDK entry points for search, speech, models, and form extraction.
- Service-specific MCP or SDK guidance
- Search and speech integration patterns
By the numbers
- Covers four primary services: AI Search, Speech, OpenAI, and Document Intelligence.
- MCP exposes three AI Search commands and two Speech commands when Azure MCP is enabled.
- Metadata version 1.1.1 from Microsoft under MIT license.
Files
Azure AI Content Safety — Java SDK Quick Reference
Condensed from azure-ai-contentsafety-java. Full patterns (blocklist management, image moderation, 8-severity)
in the azure-ai-contentsafety-java plugin skill if installed.
Install
<dependency>
<groupId>com.azure</groupId>
<artifactId>azure-ai-contentsafety</artifactId>
<version>1.1.0-beta.1</version>
</dependency>Quick Start
import com.azure.ai.contentsafety.ContentSafetyClient;
import com.azure.ai.contentsafety.ContentSafetyClientBuilder;
import com.azure.ai.contentsafety.BlocklistClient;
import com.azure.ai.contentsafety.BlocklistClientBuilder;
ContentSafetyClient client = new ContentSafetyClientBuilder()
.endpoint(endpoint).credential(credential).buildClient();Non-Obvious Patterns
- Two separate builders:
ContentSafetyClientBuilderandBlocklistClientBuilder - Image from file:
new ContentSafetyImageData().setContent(BinaryData.fromBytes(bytes)) - Image from URL:
new ContentSafetyImageData().setBlobUrl(url) - Blocklist create uses raw
BinaryData+RequestOptions(not typed model)
Best Practices
1. Blocklist changes take ~5 minutes to take effect 2. Only request needed categories to reduce latency 3. Typically block severity >= 4 for strict moderation 4. Process multiple items in parallel for throughput 5. Cache blocklist results where appropriate
--- name: azure-ai description: "Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech." license: MIT metadata: author: Microsoft version: "1.1.1" ---
Azure AI Services
Services
| Service | Use When | MCP Tools | CLI |
|---|---|---|---|
| AI Search | Full-text, vector, hybrid search | azure__search | az search |
| Speech | Speech-to-text, text-to-speech | azure__speech | - |
| OpenAI | GPT models, embeddings, DALL-E | - | az cognitiveservices |
| Document Intelligence | Form extraction, OCR | - | - |
MCP Server (Preferred)
When Azure MCP is enabled:
AI Search
azure__searchwith commandsearch_index_list- List search indexesazure__searchwith commandsearch_index_get- Get index detailsazure__searchwith commandsearch_query- Query search index
Speech
azure__speechwith commandspeech_transcribe- Speech to textazure__speechwith commandspeech_synthesize- Text to speech
If Azure MCP is not enabled: Run /azure:setup or enable via /mcp.
AI Search Capabilities
| Feature | Description |
|---|---|
| Full-text search | Linguistic analysis, stemming |
| Vector search | Semantic similarity with embeddings |
| Hybrid search | Combined keyword + vector |
| AI enrichment | Entity extraction, OCR, sentiment |
Speech Capabilities
| Feature | Description |
|---|---|
| Speech-to-text | Real-time and batch transcription |
| Text-to-speech | Neural voices, SSML support |
| Speaker diarization | Identify who spoke when |
| Custom models | Domain-specific vocabulary |
SDK Quick References
For programmatic access to these services, see the condensed SDK guides:
- AI Search: Python | TypeScript | .NET
- OpenAI: .NET
- Vision: Python | Java
- Transcription: Python
- Translation: Python | TypeScript
- Document Intelligence
Related skills
How it compares
Azure AI service router and MCP guide, not a general model fine-tuning workflow.
FAQ
Who is azure-ai for?
Developers integrating Azure AI Search, Speech, OpenAI, or Document Intelligence via MCP, CLI, or SDKs.
When should I use azure-ai?
When standing up search indexes, running vector or hybrid queries, transcribing audio, synthesizing speech, or extracting forms with OCR.
Is azure-ai safe to install?
Review the Security Audits panel on this page before installing in production.